Abstract: Electron energy loss spectroscopy (EELS) is a well established technique in electron microscopy that yields information on the elemental content of a sample in a very direct manner. One of the persisting limitations of EELS is the requirement for manual identification of core-loss edges and their corresponding elements. This can be especially bothersome in spectrum imaging, where a large amount of spectra are recorded when spatially scanning over a sample area. This paper introduces a synthetic dataset with 736,000 labeled EELS spectra, computed from available generalized oscillator strength tables, that represents 107 K, L, M or N core-loss edges and 80 chemical elements. Generic lifetime broadened peaks are used to mimic the fine structure due to band structure effects present in experimental core-loss edges. The proposed dataset is used to train and evaluate a series of neural network architectures, being a multilayer perceptron, a convolutional neural network, a U-Net, a residual neural network, a vision transformer and a compact convolutional transformer. An ensemble of neural networks is used to further increase performance. The ensemble network is used to demonstrate fully automated elemental mapping in a spectrum image, both by directly mapping the predicted elemental content and by using the predicted content as input for a physical model-based mapping.

Abstract: Microplasmas can be used for a wide range of technological applications and to improve the understanding of fundamental physics. Scanning electron microscopy, on the other hand, provides insights into the sample morphology and chemistry of materials from the mm‐ down to the nm‐scale. Combining both would provide direct insight into plasma‐sample interactions in real‐time and at high spatial resolution. Up till now, very few attempts in this direction have been made, and significant challenges remain. This work presents a stable direct current glow discharge microplasma setup built inside a scanning electron microscope. The experimental setup is capable of real‐time in situ imaging of the sample evolution during plasma operation and it demonstrates localized sputtering and sample oxidation. Further, the experimental parameters such as varying gas mixtures, electrode polarity, and field strength are explored and experimental<italic>V</italic>–<italic>I</italic>curves under various conditions are provided. These results demonstrate the capabilities of this setup in potential investigations of plasma physics, plasma‐surface interactions, and materials science and its practical applications. The presented setup shows the potential to have several technological applications, for example, to locally modify the sample surface (e.g., local oxidation and ion implantation for nanotechnology applications) on the µm‐scale.